[RFC,v2,3/3] mm/gup: introduce vaddr_pin_pages_remote(), and invoke it

Commit Message

John Hubbard Aug. 17, 2019, 2:24 a.m. UTC

From: John Hubbard <[e-mail]>

vaddr_pin_user_pages_remote() is the "vaddr_pin_pages" corresponding
variant to get_user_pages_remote(): it adds the ability to handle
FOLL_PIN, FOLL_LONGTERM, or both.

Note that the put_user_page*() requirement won't be truly required until
all of the call sites have been converted, and the tracking of pages is
activated.

Also, change process_vm_rw_single_vec() to invoke the new function.

Signed-off-by: John Hubbard <[e-mail]>
---
 include/linux/mm.h     |  5 +++++
 mm/gup.c               | 33 +++++++++++++++++++++++++++++++++
 mm/process_vm_access.c | 23 ++++++++++++++---------
 3 files changed, 52 insertions(+), 9 deletions(-)

Patch

diff --git a/include/linux/mm.h b/include/linux/mm.h
index 6e7de424bf5e..849b509e9f89 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1606,6 +1606,11 @@  int __account_locked_vm(struct mm_struct *mm, unsigned long pages, bool inc,
 long vaddr_pin_pages(unsigned long addr, unsigned long nr_pages,
 		     unsigned int gup_flags, struct page **pages,
 		     struct vaddr_pin *vaddr_pin);
+long vaddr_pin_user_pages_remote(struct task_struct *tsk, struct mm_struct *mm,
+				 unsigned long start, unsigned long nr_pages,
+				 unsigned int gup_flags, struct page **pages,
+				 struct vm_area_struct **vmas, int *locked,
+				 struct vaddr_pin *vaddr_pin);
 void vaddr_unpin_pages(struct page **pages, unsigned long nr_pages,
 		       struct vaddr_pin *vaddr_pin, bool make_dirty);
 bool mapping_inode_has_layout(struct vaddr_pin *vaddr_pin, struct page *page);
diff --git a/mm/gup.c b/mm/gup.c
index e49096d012ea..d7ce9b38178f 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -2522,3 +2522,36 @@  void vaddr_unpin_pages(struct page **pages, unsigned long nr_pages,
 	__put_user_pages_dirty_lock(pages, nr_pages, make_dirty, vaddr_pin);
 }
 EXPORT_SYMBOL(vaddr_unpin_pages);
+
+/**
+ * vaddr_pin_user_pages_remote() - pin pages by virtual address and return the
+ * pages to the user.
+ *
+ * @tsk:	the task_struct to use for page fault accounting, or
+ *		NULL if faults are not to be recorded.
+ * @mm:		mm_struct of target mm
+ * @addr:	start address
+ * @nr_pages:	number of pages to pin
+ * @gup_flags:	flags to use for the pin. Please see FOLL_* documentation in
+ *		mm.h.
+ * @pages:	array of pages returned
+ * @vaddr_pin:  If FOLL_LONGTERM is set, then vaddr_pin should point to an
+ * initialized struct that contains the owning mm and file. Otherwise, vaddr_pin
+ * should be set to NULL.
+ *
+ * This is the "vaddr_pin_pages" corresponding variant to
+ * get_user_pages_remote(), but with the ability to handle FOLL_PIN,
+ * FOLL_LONGTERM, or both.
+ */
+long vaddr_pin_user_pages_remote(struct task_struct *tsk, struct mm_struct *mm,
+				 unsigned long start, unsigned long nr_pages,
+				 unsigned int gup_flags, struct page **pages,
+				 struct vm_area_struct **vmas, int *locked,
+				 struct vaddr_pin *vaddr_pin)
+{
+	gup_flags |= FOLL_TOUCH | FOLL_REMOTE;
+
+	return __get_user_pages_locked(tsk, mm, start, nr_pages, pages, vmas,
+				       locked, gup_flags, vaddr_pin);
+}
+EXPORT_SYMBOL(vaddr_pin_user_pages_remote);
diff --git a/mm/process_vm_access.c b/mm/process_vm_access.c
index 357aa7bef6c0..e08c1f760ad4 100644
--- a/mm/process_vm_access.c
+++ b/mm/process_vm_access.c
@@ -96,7 +96,7 @@  static int process_vm_rw_single_vec(unsigned long addr,
 		flags |= FOLL_WRITE;
 
 	while (!rc && nr_pages && iov_iter_count(iter)) {
-		int pages = min(nr_pages, max_pages_per_loop);
+		int pinned_pages = min(nr_pages, max_pages_per_loop);
 		int locked = 1;
 		size_t bytes;
 
@@ -106,14 +106,18 @@  static int process_vm_rw_single_vec(unsigned long addr,
 		 * current/current->mm
 		 */
 		down_read(&mm->mmap_sem);
-		pages = get_user_pages_remote(task, mm, pa, pages, flags,
-					      process_pages, NULL, &locked);
+
+		flags |= FOLL_PIN;
+		pinned_pages = vaddr_pin_user_pages_remote(task, mm, pa,
+							   pinned_pages, flags,
+							   process_pages, NULL,
+							   &locked, NULL);
 		if (locked)
 			up_read(&mm->mmap_sem);
-		if (pages <= 0)
+		if (pinned_pages <= 0)
 			return -EFAULT;
 
-		bytes = pages * PAGE_SIZE - start_offset;
+		bytes = pinned_pages * PAGE_SIZE - start_offset;
 		if (bytes > len)
 			bytes = len;
 
@@ -122,10 +126,11 @@  static int process_vm_rw_single_vec(unsigned long addr,
 					 vm_write);
 		len -= bytes;
 		start_offset = 0;
-		nr_pages -= pages;
-		pa += pages * PAGE_SIZE;
-		while (pages)
-			put_page(process_pages[--pages]);
+		nr_pages -= pinned_pages;
+		pa += pinned_pages * PAGE_SIZE;
+
+		/* If vm_write is set, the pages need to be made dirty: */
+		vaddr_unpin_pages(process_pages, pinned_pages, NULL, vm_write);
 	}
 
 	return rc;